{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:5DSJZPIJCLBXT43555OAQFYAJZ","short_pith_number":"pith:5DSJZPIJ","schema_version":"1.0","canonical_sha256":"e8e49cbd0912c379f37def5c0817004e74efbe7ce62e4d58358baf645ce64ec5","source":{"kind":"arxiv","id":"2205.11587","version":2},"attestation_state":"computed","paper":{"title":"Bayesian error propagation for neural-net based parameter inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["astro-ph.CO"],"primary_cat":"astro-ph.IM","authors_text":"Daniela Grand\\'on, Elena Sellentin","submitted_at":"2022-05-23T19:36:55Z","abstract_excerpt":"Neural nets have become popular to accelerate parameter inferences, especially for the upcoming generation of galaxy surveys in cosmology. As neural nets are approximative by nature, a recurrent question has been how to propagate the neural net's approximation error, in order to avoid biases in the parameter inference. We present a Bayesian solution to propagating a neural net's approximation error and thereby debiasing parameter inference. We exploit that a neural net reports its approximation errors during the validation phase. We capture the thus reported approximation errors via the highes"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2205.11587","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"astro-ph.IM","submitted_at":"2022-05-23T19:36:55Z","cross_cats_sorted":["astro-ph.CO"],"title_canon_sha256":"93751ce191fcca7fb860b84fa0e9180e8f735c8e23a3be5d26c2944beee93250","abstract_canon_sha256":"bf3a6c096a567a3a6fe6234b991cb72976b082f0eb8da66d7a5fdcc580a63e1c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:42:35.870805Z","signature_b64":"VmEBWmj2o12h5SBgEJoWU4p1YjXuooqYW3OibsF+GIXP/Xu7QKOmDj7N5PfqdCRWQ2QAwsJbtaph/P9iYYfnCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e8e49cbd0912c379f37def5c0817004e74efbe7ce62e4d58358baf645ce64ec5","last_reissued_at":"2026-07-05T04:42:35.870024Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:42:35.870024Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bayesian error propagation for neural-net based parameter inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["astro-ph.CO"],"primary_cat":"astro-ph.IM","authors_text":"Daniela Grand\\'on, Elena Sellentin","submitted_at":"2022-05-23T19:36:55Z","abstract_excerpt":"Neural nets have become popular to accelerate parameter inferences, especially for the upcoming generation of galaxy surveys in cosmology. As neural nets are approximative by nature, a recurrent question has been how to propagate the neural net's approximation error, in order to avoid biases in the parameter inference. We present a Bayesian solution to propagating a neural net's approximation error and thereby debiasing parameter inference. We exploit that a neural net reports its approximation errors during the validation phase. We capture the thus reported approximation errors via the highes"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.11587","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2205.11587/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2205.11587","created_at":"2026-07-05T04:42:35.870112+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.11587v2","created_at":"2026-07-05T04:42:35.870112+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.11587","created_at":"2026-07-05T04:42:35.870112+00:00"},{"alias_kind":"pith_short_12","alias_value":"5DSJZPIJCLBX","created_at":"2026-07-05T04:42:35.870112+00:00"},{"alias_kind":"pith_short_16","alias_value":"5DSJZPIJCLBXT435","created_at":"2026-07-05T04:42:35.870112+00:00"},{"alias_kind":"pith_short_8","alias_value":"5DSJZPIJ","created_at":"2026-07-05T04:42:35.870112+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5DSJZPIJCLBXT43555OAQFYAJZ","json":"https://pith.science/pith/5DSJZPIJCLBXT43555OAQFYAJZ.json","graph_json":"https://pith.science/api/pith-number/5DSJZPIJCLBXT43555OAQFYAJZ/graph.json","events_json":"https://pith.science/api/pith-number/5DSJZPIJCLBXT43555OAQFYAJZ/events.json","paper":"https://pith.science/paper/5DSJZPIJ"},"agent_actions":{"view_html":"https://pith.science/pith/5DSJZPIJCLBXT43555OAQFYAJZ","download_json":"https://pith.science/pith/5DSJZPIJCLBXT43555OAQFYAJZ.json","view_paper":"https://pith.science/paper/5DSJZPIJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.11587&json=true","fetch_graph":"https://pith.science/api/pith-number/5DSJZPIJCLBXT43555OAQFYAJZ/graph.json","fetch_events":"https://pith.science/api/pith-number/5DSJZPIJCLBXT43555OAQFYAJZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5DSJZPIJCLBXT43555OAQFYAJZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5DSJZPIJCLBXT43555OAQFYAJZ/action/storage_attestation","attest_author":"https://pith.science/pith/5DSJZPIJCLBXT43555OAQFYAJZ/action/author_attestation","sign_citation":"https://pith.science/pith/5DSJZPIJCLBXT43555OAQFYAJZ/action/citation_signature","submit_replication":"https://pith.science/pith/5DSJZPIJCLBXT43555OAQFYAJZ/action/replication_record"}},"created_at":"2026-07-05T04:42:35.870112+00:00","updated_at":"2026-07-05T04:42:35.870112+00:00"}